帮助 关于我们

返回检索结果

基于特征点不确定性加权误差的位姿估计新方法
A new pose estimation method based on uncertainty-weighted errors of the feature points

查看参考文献21篇

文摘 计算机视觉中一般是利用优化技术最小化目标函数来估计位姿,目标函数通常是由图像平面上特征点重投影误差构成,并且假设测量噪声是各向同性且独立同分布的高斯噪声,所得到的位姿是在该假设条件下的极大似然最优估计。然而,在实际应用中这种假设并不总是成立,测量噪声通常是各向异性且非独立同分布,而且常常具有很强的方向性。为此,本文提出了一种新的特征点位姿估计方法,首先对特征点的方向不确定性建模,然后将方向不确定性融入到重投影误差中,构造基于不确定性加权误差的新目标函数,最后利用Levenberg-Marquardt算法优化目标函数求解位姿。大量实验结果表明,本方法可以适应不同程度的方向不确定性,精度优于现有迭代方法。而且随着不确定性的增加,位姿解的精度并没有明显变差。
其他语种文摘 Pose estimation problem in computer vision is often solved by minimizing cost functions that combine the reprojection errors in the 2D images,but the cost functions are based on the assumption that measurement noises are isotropic,independent and identically distributed(i.i.d.) at every 2D feature point,so the solution of pose becomes statistically meaningful and optimal in the sense of maximum likelihood.However,this assumption is rarely the case in real applications,where the positional noise not only varies at different features,but also has strong directionality.In this situation,we propose a new pose estimation method that incorporates the directional uncertainty of the points into reprojection errors and constructs a new uncertainty-weighted cost function.The method can adapt to varying degrees of directional uncertainty and guarantee more accurate results.In particular,unlike other reprojection-error-based methods,our method does not degrade with increase in directionality of uncertainty.Finally we demonstrate the effectiveness of the method by experiments on synthetic data that contains high directional uncertainty.
来源 光电子·激光 ,2012,23(7):1348-1355 【核心库】
关键词 位姿估计 ; PnP问题 ; 方向不确定性 ; 不确定性加权误差
地址

中国科学院沈阳自动化研究所, 中国科学院光电信息处理重点实验室;;辽宁省图像理解与视觉计算重点实验室, 辽宁, 沈阳, 110016

语种 中文
ISSN 1005-0086
学科 自动化技术、计算机技术
基金 国家自然科学基金
文献收藏号 CSCD:4615173

参考文献 共 21 共2页

1.  黄邦奎. 多传感器线结构光视觉测量系统全局校准. 光电子·激光,2010,21(6):894-897 被引 1 次    
2.  肖永亮. 基于凸松弛全局优化算法的视觉测量位姿估计. 光电子·激光,2010,21(6):894-897 被引 1 次    
3.  Hartley R I. Multiple view geometry in computer vision,2004:121-132 被引 1 次    
4.  Fischler M A. Random sample consensus:a paradigm for model fitting with applications to image analysis and automated cartography. Communications ACM,1981,24(6):381-395 被引 1168 次    
5.  Vincent L. EPnP:an accurate O (n)solution to the PnP problem. International Journal of Computer Vision,2009,81(2):155-166 被引 9 次    
6.  Kneip L. A novel parametrization of the perspective-three-point problem for a direct computation of absolute camera position and orientation. Proceedings of IEEE Conference on Computer Vision and Pattern Recognition,2011:2969-2976 被引 2 次    
7.  Kukelova Z. Closed-form solutions to the minimal absolute pose problems with known vertical direction. Proceedings of Asian Conference on Computer Vision,2010:216-229 被引 1 次    
8.  Joel A. A direct least-squares(dls)solution for PnP. Proceedings of International Conference on Computer Vision,2011:383-390 被引 1 次    
9.  Carl O. Optimal estimation of perspective camera pose. Proceedings of International Conference on Pattern Recognition,2006:5-8 被引 1 次    
10.  Olof E. Robust optimal pose estimation. Proceedings of European Conference on Computer Vision,2008:141-153 被引 1 次    
11.  Lu C P. Fast and globally convergent pose estimation from video images. IEEE Transactions on Pattern Analysis and Machine Intelligence,2000,22(6):610-622 被引 111 次    
12.  Engels C. Bundle adjustment rules. Proceedings of Congress of the International Society for Photogrammetry and Remote Sensing,2006:534-541 被引 1 次    
13.  Schweighofer G. Globally Optimal O(n)Solution to the PnP Problem for General Camera Models. Proceedings of British Machine Vision Conference,2008:1-10 被引 2 次    
14.  Hartley R I. Global optimization through rotation space search. International Journal of Computer Vision,2009,81(1):64-79 被引 10 次    
15.  Hartley R I. Optimal algorithms in multiview geometry. Proceedings of Asian Conference on Computer Vision,2007:13-34 被引 1 次    
16.  Anandan P. Factorization with uncertainty. International Journal of Computer Vision,2002,49(2/3):101-116 被引 5 次    
17.  Shi J. Good features to track. Proceedings of IEEE Conference on Computer Vision and Pattern Recognition,1994:593-600 被引 21 次    
18.  Steele R M. Feature uncertainty arising from covariant image noise. Proceedings of IEEE Conference on Computer Vision and Pattern Recognition,2005:1063-1070 被引 1 次    
19.  Lourakis M. A C++version of Levenberg-Marquardt. 被引 1 次    
20.  Burton S. An implementation of Levenberg-Marquardt 被引 1 次    
引证文献 5 篇

1 李凯 基于蒙特卡洛法的圆光栅测角误差分析与补偿 光电子·激光,2014,25(7):1381-1388
被引 7 次

2 刘冬雨 空间机械臂在轨维修的视觉伺服操控策略 机器人,2018,40(5):742-749
被引 4 次

显示所有5篇文献

论文科学数据集
PlumX Metrics
相关文献

 作者相关
 关键词相关
 参考文献相关

版权所有 ©2008 中国科学院文献情报中心 制作维护：中国科学院文献情报中心
地址：北京中关村北四环西路33号 邮政编码：100190 联系电话：(010)82627496 E-mail:cscd@mail.las.ac.cn 京ICP备05002861号-4 | 京公网安备11010802043238号